EstimatorSpec
Understand how to evaluate regression models using mean squared error and how to implement TensorFlow's EstimatorSpec for managing training, evaluation, and prediction tasks. This lesson guides you through organizing model outputs to support scalable machine learning workflows.
We'll cover the following...
Chapter Goals:
- Learn how to evaluate a regression model
- Use the
EstimatorSpecobject to organize results from training, evaluation, and prediction
A. Regression evaluation
Unlike classification models, we can’t use the accuracy metric to evaluate regression. Since the output of regression models is a real number, rather than a class prediction, there’s no definite way to say what is “correct” or “incorrect”.
However, we can tell how good a model output is based on its distance from the corresponding label. For example, if the label for some data observation was 0.2 and the model returned 0.199, the prediction is excellent. On the other hand, if the model returned 812.11, the prediction is likely very poor. ...